一键导入
catchup
Re-ground in this repo's current state and report before making any change. Use when the owner says catchup or asks where things stand.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Re-ground in this repo's current state and report before making any change. Use when the owner says catchup or asks where things stand.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | catchup |
| description | Re-ground in this repo's current state and report before making any change. Use when the owner says catchup or asks where things stand. |
Run the catchup operator defined in this repo's AGENTS.md (Operator
Requests): re-read AGENTS.md (the Prime Invariants in full),
.agents/state.md, and the active repo docs, then summarize the current
state, the next action, blockers, and one proposed first action. Make no
changes until the human responds. AGENTS.md is the authoritative
definition; this skill is only a pointer.
Compare a doc, decision, or guidance claim against repo evidence and fix or report the conflict; also the deliberate state-hygiene pass. Use when the owner says drift.
Fast save-my-place snapshot of .agents/state.md so the next session resumes without chat context. Use when the owner says handoff or a session is wrapping up.
Draft or update a durable plan before broad implementation work. Use when the owner says plan.
Run the reviewloop playbook with a named reviewer agent to review the current finding. Use when the owner says review <agent>.
Record a settled durable decision in .agents/decisions.md and update affected guidance. Use when the owner says decision.
Read the named playbook under .agents/playbooks/ and follow it. Use when the owner says playbook <name>.